Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020159947 - MODEL-FREE CONTROL OF DYNAMICAL SYSTEMS WITH DEEP RESERVOIR COMPUTING

Publication Number WO/2020/159947
Publication Date 06.08.2020
International Application No. PCT/US2020/015350
International Filing Date 28.01.2020
IPC
G06N 3/04 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
G05B 19/042 2006.1
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
19Programme-control systems
02electric
04Programme control other than numerical control, i.e. in sequence controllers or logic controllers
042using digital processors
CPC
B25J 9/163
BPERFORMING OPERATIONS; TRANSPORTING
25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
9Programme-controlled manipulators
16Programme controls
1628characterised by the control loop
163learning, adaptive, model based, rule based expert control
G05B 13/021
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
13Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
02electric
0205not using a model or a simulator of the controlled system
021in which a variable is automatically adjusted to optimise the performance
G05B 13/026
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
13Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
02electric
0205not using a model or a simulator of the controlled system
026using a predictor
G05B 13/027
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
13Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
02electric
0265the criterion being a learning criterion
027using neural networks only
G05B 13/0285
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
13Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
02electric
0265the criterion being a learning criterion
0285using neural networks and fuzzy logic
G05B 19/0426
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
19Programme-control systems
02electric
04Programme control other than numerical control, i.e. in sequence controllers or logic controllers
042using digital processors
0426Programming the control sequence
Applicants
  • OHIO STATE INNOVATION FOUNDATION [US]/[US]
  • POTOMAC RESEARCH LLC [US]/[US]
Inventors
  • CANADAY, Daniel
  • POMERANCE, Andrew, Joseph
  • GRIFFITH, Aaron, Geoffrey
  • GAUTHIER, Daniel
Agents
  • WALDMAN, Jonathan, M.
  • HALL, Miles, E.
  • MEUNIER, Andrew, T.
  • CARLIN, Gregory, J.
  • CURFMAN, Christopher, L.
Priority Data
62/797,56128.01.2019US
62/836,31019.04.2019US
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) MODEL-FREE CONTROL OF DYNAMICAL SYSTEMS WITH DEEP RESERVOIR COMPUTING
(FR) COMMANDE SANS MODÈLE DE SYSTÈMES DYNAMIQUES AVEC CALCUL EN RÉSERVOIR PROFOND
Abstract
(EN) A technique is provided for control of a nonlinear dynamical system to an arbitrary trajectory. The technique does not require any knowledge of the dynamical system, and thus is completely model-free. When applied to a chaotic system, it is capable of stabilizing unstable periodic orbits (UPOs) and unstable steady states (USSs), controlling orbits that require non-vanishing control signal, synchronization to other chaotic systems, and so on. It is based on a type of recurrent neural network (RNN) known as a reservoir computer (RC), which, as shown, is capable of directly learning how to control an unknown system. Precise control to a desired trajectory is obtained by iteratively adding layers to the controller, forming a deep recurrent neural network.
(FR) L'invention concerne une technique de commande d'un système dynamique non linéaire sur une trajectoire arbitraire. La technique ne nécessite aucune connaissance du système dynamique, et est ainsi complètement sans modèle. Lors de l'application à un système chaotique, elle est capable de stabiliser des orbites périodiques instables (UPO) et des états stationnaires instables (USS), de commander des orbites qui nécessitent un signal de commande qui ne s'annule pas, de se synchroniser avec d'autres systèmes chaotiques, et ainsi de suite. Elle est basée sur un type de réseau neuronal récurrent (RNN) connu sous le nom de calculateur en réservoir (RC), qui, comme illustré, est capable d'apprendre directement comment commander un système inconnu. Une commande précise d'une trajectoire souhaitée est obtenue en ajoutant itérativement des couches au contrôleur, ce qui forme un réseau neuronal récurrent profond.
Related patent documents
Latest bibliographic data on file with the International Bureau